abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
DARE v4 is the product-level orchestrator for a research run. It turns a user request into a controlled sequence of North Star crystallization, executable specification, and phase-by-phase execution.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill de-anthropocentric-research-engine --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/de-anthropocentric-research-engineContext preview
The summary Claude sees to decide when to auto-load this skill.
DARE v4 is the product-level orchestrator for a research run. It turns a user request into a controlled sequence of North Star crystallization, executable specification, and phase-by-phase execution.
name: de-anthropocentric-research-engine description: "DARE v4 is the product-level orchestrator for a research run. It turns a user request into a controlled sequence of North Star crystallization, executable specification, and phase-by-phase execution."
DARE v4 is the product-level orchestrator for a research run. It turns a user request into a controlled sequence of North Star crystallization, executable specification, and phase-by-phase execution. It is not a scientific graph node and must not be counted among the 267 tactic/SOP nodes.
required: [user_request] optional: [existing_context, north_star, research_brief, constraints] constraints: - a run may start with an existing North Star only when it is explicit and user-confirmed - execution requires a current SpecView reconstructed from checkpoint events
DARE enforces this order and does not skip a phase:
1. **North Star**: if a confirmed North Star and ResearchBrief are absent, collect and crystallize them from the user request. If they are present, verify that they still describe the request. 2. **Spec**: You MUST load skill `research-catalog` to expose the available tactics. You MUST load skill `write-research-spec` to turn the confirmed North Star, ResearchBrief, and user constraints into an executable Research Spec. Do not execute research while this phase is incomplete. 3. **Execution**: after the user approves the Spec, You MUST load skill `execute-research-spec` to execute its phases and checkpoints. Do not select a tactic directly from the flat skill directory.
At every phase boundary, record the decision and its reason in the current Phase checkpoint event stream. A plan change is an appended `decisions` event, never an edit to an earlier checkpoint. The product shell may present progress, but scientific conclusions remain in tactic/SOP Delta fields.
produces: - confirmed_north_star - research_brief - spec_view - phase_execution_results - final_research_summary state_delta_fields: - findings - evidence_updates - hypothesis_updates - assumption_updates - uncertainties - decisions - open_questions - recommended_jumps
Missing intent or scope blocks entry to specification and returns `NEEDS_CONTEXT`. An unmet completion gate keeps the current stage active. A triggered backtrack condition is presented for user confirmation and, if approved, is recorded as a new decision before execution returns to the target stage. DARE never treats an empty result, elapsed time, or an execution interruption as stage completion.
This entry layer is installed under `skills/` alongside the 267 tactic and SOP nodes. It is not a graph node, does not create a third scientific layer, and does not replace tactic or SOP contracts.
The complete research orchestration system for AI-native science. What It Does Design Philosophy Architecture (v3.2.2) Quick Start Configuration Roadmap License DARE is not a tool that helps you do research. It is the researcher.
Repo: yogsoth-ai/de-anthropocentric-research-engine
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Evaluate competing arguments against stated criteria and produce a reasoned verdict with uncertainty.
Move a scientific object up/down in abstraction or narrow/broaden selected scope dimensions (population, mechanism, context, outcome, timeframe, system…
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target, escalation depth,…
Aggregate criterion or comparison results into an ordered recommendation under an explicit rule.
Abstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms.